Super-Resolution

Papers

Super-Resolution.Benckmark

• intro: Benchmark and resources for single super-resolution algorithms
• github: https://github.com/huangzehao/Super-Resolution.Benckmark

Image Super-Resolution Using Deep Convolutional Networks

• intro: Microsoft Research
• project page: http://mmlab.ie.cuhk.edu.hk/projects/SRCNN.html
• arxiv: http://arxiv.org/abs/1501.00092
• training code: http://mmlab.ie.cuhk.edu.hk/projects/SRCNN/SRCNN_train.zip
• test code: http://mmlab.ie.cuhk.edu.hk/projects/SRCNN/SRCNN_v1.zip
• github(Keras): https://github.com/titu1994/Image-Super-Resolution

Learning a Deep Convolutional Network for Image Super-Resolution

• Baidu-pan: http://pan.baidu.com/s/1c0k0wRu

Shepard Convolutional Neural Networks

• paper: https://papers.nips.cc/paper/5774-shepard-convolutional-neural-networks.pdf
• github: https://github.com/jimmy-ren/vcnn_double-bladed/tree/master/applications/Shepard_CNN

Bidirectional Recurrent Convolutional Networks for Multi-Frame Super-Resolution

• intro: NIPS 2015
• paper: https://papers.nips.cc/paper/5778-bidirectional-recurrent-convolutional-networks-for-multi-frame-super-resolution

Deeply-Recursive Convolutional Network for Image Super-Resolution

• intro: CVPR 2016
• arxiv: http://arxiv.org/abs/1511.04491
• paper: http://cv.snu.ac.kr/publication/conf/2016/DRCN_CVPR2016.pdf

Accurate Image Super-Resolution Using Very Deep Convolutional Networks

• intro: CVPR 2016 Oral
• project page: http://cv.snu.ac.kr/research/VDSR/
• arxiv: http://arxiv.org/abs/1511.04587
• code: http://cv.snu.ac.kr/research/VDSR/VDSR_code.zip
• github: https://github.com/huangzehao/caffe-vdsr
• github(Torch): https://github.com/pby5/vdsr_torch

Super-Resolution with Deep Convolutional Sufficient Statistics

• arxiv: http://arxiv.org/abs/1511.05666

Deep Depth Super-Resolution : Learning Depth Super-Resolution using Deep Convolutional Neural Network

• arxiv: http://arxiv.org/abs/1607.01977

Local- and Holistic- Structure Preserving Image Super Resolution via Deep Joint Component Learning

• arxiv: http://arxiv.org/abs/1607.07220

End-to-End Image Super-Resolution via Deep and Shallow Convolutional Networks

• arxiv: http://arxiv.org/abs/1607.07680

Accelerating the Super-Resolution Convolutional Neural Network

• intro: speed up of more than 40 times with even superior restoration quality, real-time performance on a generic CPU
• project page: http://mmlab.ie.cuhk.edu.hk/projects/FSRCNN.html
• arxiv: http://arxiv.org/abs/1608.00367

srez: Image super-resolution through deep learning

• github: https://github.com/david-gpu/srez

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

• intro: CVPR 2017 Oral
• arxiv: https://arxiv.org/abs/1609.04802
• github: https://github.com/tensorlayer/SRGAN
• github(Torch): https://github.com/leehomyc/Photo-Realistic-Super-Resoluton
• github: https://github.com/junhocho/SRGAN
• github(Keras): https://github.com/titu1994/Super-Resolution-using-Generative-Adversarial-Networks
• github: https://github.com/buriburisuri/SRGAN

Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network

• intro: CVPR 2016
• arxiv: http://arxiv.org/abs/1609.05158
• github: https://github.com/Tetrachrome/subpixel

Is the deconvolution layer the same as a convolutional layer?

• intro: A note on Real­Time Single Image and Video Super­Resolution Using an Efficient Sub­Pixel Convolutional Neural Network.
• arxiv: http://arxiv.org/abs/1609.07009

Amortised MAP Inference for Image Super-resolution

• arxiv: https://arxiv.org/abs/1610.04490

Real-Time Video Super-Resolution with Spatio-Temporal Networks and Motion Compensation

• arxiv: https://arxiv.org/abs/1611.05250

Super-Resolution on Satellite Imagery using Deep Learning

• part 1: https://medium.com/the-downlinq/super-resolution-on-satellite-imagery-using-deep-learning-part-1-ec5c5cd3cd2#.4oxn9pafu

Neural Enhance: Super Resolution for images using deep learning.

• github: https://github.com/alexjc/neural-enhance
• docker: https://github.com/alexjc/neural-enhance/blob/master/docker-cpu.df

Texture Enhancement via High-Resolution Style Transfer for Single-Image Super-Resolution

• intro: Digital Media & Communications R&D Center, Samsung Electronics, Seoul, Korea
• arxiv: https://arxiv.org/abs/1612.00085

EnhanceNet: Single Image Super-Resolution through Automated Texture Synthesis

• arxiv: https://arxiv.org/abs/1612.07919

Learning a Mixture of Deep Networks for Single Image Super-Resolution

• project page: http://www.ifp.illinois.edu/~dingliu2/accv2016/
• arxiv: https://arxiv.org/abs/1701.00823
• code: http://www.ifp.illinois.edu/~dingliu2/accv2016/codes/python_accv2016.zip

Dual Recovery Network with Online Compensation for Image Super-Resolution

• arxiv: https://arxiv.org/abs/1701.05652

Super-resolution Using Constrained Deep Texture Synthesis

• intro: Brown University & Georgia Institute of Technology
• arxiv: https://arxiv.org/abs/1701.07604

Pixel Recursive Super Resolution

• arxiv: https://arxiv.org/abs/1702.00783
• github(Tensorflow): https://github.com/nilboy/pixel-recursive-super-resolution

GUN: Gradual Upsampling Network for single image super-resolution

• arxiv: https://arxiv.org/abs/1703.04244

Single Image Super-resolution with a Parameter Economic Residual-like Convolutional Neural Network

• intro: Extentions of mmm 2017 paper
• arxiv: https://arxiv.org/abs/1703.08173

Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution

• intro: CVPR 2017
• project page(code+dataset): http://vllab1.ucmerced.edu/~wlai24/LapSRN/
• arxiv: https://arxiv.org/abs/1704.03915
• github(Matlab+MatConvNet): https://github.com/phoenix104104/LapSRN

Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks

• project page: http://vllab.ucmerced.edu/wlai24/LapSRN/
• arxiv: https://arxiv.org/abs/1710.01992
• github: https://github.com/phoenix104104/LapSRN

Single Image Super-Resolution Using Multi-Scale Convolutional Neural Network

• intro: South China University of Technology
• arxiv: https://arxiv.org/abs/1705.05084

Super-Resolution via Deep Learning

• intro: COMSATS Institute of IT (CIIT)
• arxiv: https://arxiv.org/abs/1706.09077

High-Quality Face Image SR Using Conditional Generative Adversarial Networks

https://arxiv.org/abs/1707.00737

Enhanced Deep Residual Networks for Single Image Super-Resolution

• intro: CVPR 2017 workshop. Best paper award of the NTIRE2017 workshop, and the winners of the NTIRE2017 Challenge on Single Image Super-Resolution
• arxiv: https://arxiv.org/abs/1707.02921
• paper: http://cv.snu.ac.kr/publication/conf/2017/EDSR_fixed.pdf
• github: https://github.com/LimBee/NTIRE2017

Fast and Accurate Image Super Resolution by Deep CNN with Skip Connection and Network in Network

• arxiv: https://arxiv.org/abs/1707.05425
• github(Tensorflow): https://github.com/jiny2001/dcscn-super-resolution

Single Image Super-Resolution with Dilated Convolution based Multi-Scale Information Learning Inception Module

• intro: ICIP 2017
• arxiv: https://arxiv.org/abs/1707.07128

Attention-Aware Face Hallucination via Deep Reinforcement Learning

https://arxiv.org/abs/1708.03132

CISRDCNN: Super-resolution of compressed images using deep convolutional neural networks

https://arxiv.org/abs/1709.06229

Deep Inception-Residual Laplacian Pyramid Networks for Accurate Single Image Super-Resolution

• intro: Chongqing University
• arxiv: https://arxiv.org/abs/1711.05431

D-PCN: Parallel Convolutional Neural Networks for Image Recognition in Reverse Adversarial Style

{https://arxiv.org/abs/1711.04237}(https://arxiv.org/abs/1711.04237)

CT-SRCNN: Cascade Trained and Trimmed Deep Convolutional Neural Networks for Image Super Resolution

• intro: IEEE Winter Conf. on Applications of Computer Vision (WACV) 2018, Lake Tahoe, USA
• arxiv: https://arxiv.org/abs/1711.04048

FSRNet: End-to-End Learning Face Super-Resolution with Facial Priors

• intro: CVPR 2018 spotlight
• arxiv: https://arxiv.org/abs/1711.10703
• github: https://github.com/tyshiwo/FSRNet

A Frequency Domain Neural Network for Fast Image Super-resolution

https://arxiv.org/abs/1712.03037

SRPGAN: Perceptual Generative Adversarial Network for Single Image Super Resolution

https://arxiv.org/abs/1712.05927

“Zero-Shot” Super-Resolution using Deep Internal Learning

• project page: http://www.wisdom.weizmann.ac.il/~vision/zssr/
• arxiv: https://arxiv.org/abs/1712.06087
• github: https://github.com/jacobgil/pytorch-zssr

Super-Resolution with Deep Adaptive Image Resampling

https://arxiv.org/abs/1712.06463

SRPGAN: Perceptual Generative Adversarial Network for Single Image Super Resolution

• intro: Peking Univeristy
• arxiv: https://arxiv.org/abs/1712.05927

SESR: Single Image Super Resolution with Recursive Squeeze and Excitation Networks

• intro: ICPR 2018
• arxiv: https://arxiv.org/abs/1801.10319

Deep Image Super Resolution via Natural Image Priors

https://arxiv.org/abs/1802.02721

Residual Dense Network for Image Super-Resolution

• intro: CVPR 2018
• arxiv: https://arxiv.org/abs/1802.08797

Deep Back-Projection Networks For Super-Resolution

• intro: CVPR 2018
• arxiv: https://arxiv.org/abs/1803.02735

Fast, Accurate, and, Lightweight Super-Resolution with Cascading Residual Network

https://arxiv.org/abs/1803.08664

Fast and Accurate Single Image Super-Resolution via Information Distillation Network

• intro: CVPR 2018
• arxiv: https://arxiv.org/abs/1803.09454

Deep Residual Networks with a Fully Connected Recon-struction Layer for Single Image Super-Resolution

https://arxiv.org/abs/1805.10143

Adaptive Importance Learning for Improving Lightweight Image Super-resolution Network

https://arxiv.org/abs/1806.01576

Image Super-Resolution Using Very Deep Residual Channel Attention Networks

• intro: ECCV 2018
• arxiv: https://arxiv.org/abs/1807.02758

An Attention-Based Approach for Single Image Super Resolution

https://arxiv.org/abs/1807.06779

The Unreasonable Effectiveness of Texture Transfer for Single Image Super-resolution

https://arxiv.org/abs/1808.00043

Deep Learning for Single Image Super-Resolution: A Brief Review

https://arxiv.org/abs/1808.03344

Improving Super-Resolution Methods via Incremental Residual Learning

https://arxiv.org/abs/1808.07110

Deep Learning-based Image Super-Resolution Considering Quantitative and Perceptual Quality

• intro: Won the 2nd place for Region 2 in the PIRM Challenge on Perceptual Super Resolution at ECCV 2018
• arxiv: https://arxiv.org/abs/1809.04789
• github: https://github.com/idearibosome/tf-perceptual-eusr

Generative adversarial network-based image super-resolution using perceptual content losses

• intro: Won the 2nd place for Region 1 in the PIRM Challenge on Perceptual Super Resolution at ECCV 2018
• arxiv: https://arxiv.org/abs/1809.04783

Channel-wise and Spatial Feature Modulation Network for Single Image Super-Resolution

https://arxiv.org/abs/1809.11130

Triple Attention Mixed Link Network for Single Image Super Resolution

https://arxiv.org/abs/1810.03254

Fast, Accurate and Lightweight Super-Resolution with Neural Architecture Search

https://arxiv.org/abs/1901.07261

Feedback Network for Image Super-Resolution

• intro: CVPR 2019
• arxiv: https://arxiv.org/abs/1903.09814
• github(official, Pytorch): https://github.com/Paper99/SRFBN_CVPR19

Video Super-resolution

Detail-revealing Deep Video Super-resolution

• arxiv: https://arxiv.org/abs/1704.02738
• github: https://github.com/jiangsutx/SPMC_VideoSR

End-to-End Learning of Video Super-Resolution with Motion Compensation

• intro: GCPR 2017
• arxiv: https://arxiv.org/abs/1707.00471

Frame-Recurrent Video Super-Resolution

https://arxiv.org/abs/1801.04590

Photorealistic Video Super Resolution

https://arxiv.org/abs/1807.07930

Recurrent Back-Projection Network for Video Super-Resolution

• intro: CVPR 2019
• keywords: Vimeo90k
• project page: https://alterzero.github.io/projects/RBPN.html
• arxiv: https://arxiv.org/abs/1903.10128
• github: https://github.com/alterzero/RBPN-PyTorch

Fast Spatio-Temporal Residual Network for Video Super-Resolution

• intro: CVPR 2019
• arxiv: https://arxiv.org/abs/1904.02870

Projects

waifu2x

• intro: Image Super-Resolution for Anime-Style Art
• github: https://github.com/nagadomi/waifu2x